CN109297499A - Lane model building method, device and computer can storage mediums - Google Patents
Lane model building method, device and computer can storage mediums Download PDFInfo
- Publication number
- CN109297499A CN109297499A CN201810950573.9A CN201810950573A CN109297499A CN 109297499 A CN109297499 A CN 109297499A CN 201810950573 A CN201810950573 A CN 201810950573A CN 109297499 A CN109297499 A CN 109297499A
- Authority
- CN
- China
- Prior art keywords
- lane
- vehicle
- real time
- time position
- precision map
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention disclose a kind of lane model building method, device and computer can storage medium, the method determines vehicle in the real time position of high-precision map;Lane configurations are extracted in the form point information of the high-precision map according to the real time position;It is located at the coordinate set of vehicle axis system according to form point information architecture lane;It converts and communicates the coordinate set to vehicle CAN bus.The present invention provides the basic data model of more accurately environment sensing, behaviour decision making by the combination of accurately diagram data and vehicle location information for the automatic Pilot of vehicle.
Description
Technical field
The present invention relates to automatic Pilot technical field, in particular to passing through vehicle location information and high-precision map
Construction method, device and the computer that the combination of data constructs the lane model of high environment sensing capability can storage medium devices.
Background technique
Accurately diagram data can serve active safety and automatic Pilot technology;It includes abundant and high-precision vehicle
Diatom information, form point, color, actual situation, lane change rule etc..
Three lanes model is the lane model of automatic Pilot field classics;It extracts three lanes by Visual identification technology
Lane line equation, lane sideline color and the information such as actual situation, lane change rule.Automatic Pilot application end can be based on above-mentioned
Information carries out lane holding, lane change control and deviated route early warning etc..
The building of traditional three lanes model is limited to Visual identification technology, the traffic member such as vehicle, pedestrian and board of blocking the way
Element;When vehicle running environment is bad, visual identity is influenced, causes the error of recognition result larger;In installation site and itself
Under the limitation of investigative range, the dead angle of detection is certainly existed;When lane sideline blocked by barrier, is stained, the knot of identification
Fruit just will appear mistake.
Summary of the invention
The embodiment of the present invention at least provides a kind of lane model building method, and being able to solve in Vehicular automatic driving should acquire
Dynamic data be blocked, cause possible erroneous decision problem.
The specific implementation of above-described embodiment, as described below.
The described method includes:
Determine vehicle in the real time position of high-precision map;
Lane configurations are extracted in the form point information of the high-precision map according to the real time position;
It is located at the coordinate set of vehicle axis system according to form point information architecture lane;
It converts and communicates the coordinate set to vehicle CAN bus.
In some embodiments disclosed by the invention,
Real time position of the determination vehicle in high-precision map, comprising:
Obtain the location data of vehicle;
Vehicle is matched in the real time position of the high-precision map according to the location data.
In some embodiments disclosed by the invention,
Described extracts lane configurations in the form point information of the high-precision map according to the real time position, comprising:
Current lane where extracting vehicle according to the real time position and the adjacent lane positioned at the current lane two sides
Form point information.
In some embodiments disclosed by the invention,
The coordinate set for being located at vehicle axis system according to form point information architecture lane, comprising:
The map coordinates system of the high-precision map is converted as vehicle body coordinate system,
It is calculated using curve matching and generates lane line equation;
The conversion simultaneously communicates the coordinate set to vehicle CAN bus, comprising:
It converts and communicates the lane line equation to vehicle CAN bus.
In some embodiments disclosed by the invention,
Described generates lane line equation using curve fitting algorithm, comprising:
The cubic polynomial of lane line equation is generated using the curve fitting algorithm of cubic Bezier principle,
The expression formula of the cubic polynomial is y=C0+C1*X+C2*X*X+C3*X*X*X, and the value range of X is MinX
To MinX,
Wherein equation parameter includes that C0, C1, C3, C4 are coefficient, and X, Y are vehicle body coordinate system coordinate, and Minx is the minimum of X
Value, MaxX are the maximum value of X;
The conversion simultaneously communicates the coordinate set to vehicle CAN bus, comprising:
It converts and communicates the cubic polynomial and equation parameter to vehicle CAN bus.
In some embodiments disclosed by the invention,
The curve fitting algorithm using cubic Bezier principle generates the cubic polynomial of lane line equation, rear
Include:
The form point information is substituted into the cubic polynomial, calculates the least mean-square error of the cubic polynomial
For equation parameter.
In some embodiments disclosed by the invention,
Described extracts lane configurations in the form point information of the high-precision map according to the real time position, further includes:
Lane configurations are extracted in the attribute data of the high-precision map according to the real time position;
The conversion simultaneously communicates the coordinate set to vehicle CAN bus, further includes:
It converts and communicates the attribute data to vehicle CAN bus.
In some embodiments disclosed by the invention,
The attribute data includes at least the one or more of actual situation, color and the lane change rule of lane line.
The present embodiment separately provide a kind of computer can storage medium, for storing instruction, described instruction is executed by processor
The step of Shi Shixian above method.
The present embodiment separately provides a kind of lane model construction device, and described device includes:
Mapping module, real time position of the load location data in high-precision map-matched automobile;
Acquisition module extracts lane configurations in the form point information of high-precision map according to real time position;
Model construction module is located at the coordinate set of vehicle axis system according to form point information architecture lane;
Communication module is converted and communicates coordinate set to vehicle CAN bus.
For above scheme, the present invention is by being referring to the drawings described in detail disclosed exemplary embodiment, also
The other feature and its advantage for making the embodiment of the present invention understand.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is the flow chart of embodiment one;
Fig. 2 is the schematic diagram of earth coordinates;
Fig. 3 is the schematic diagram of vehicle body coordinate system.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is implemented
The component of example can be arranged and be designed with a variety of different configurations.
Therefore, the detailed description of the embodiment of the present invention provided in the accompanying drawings is not intended to limit below claimed
The scope of the present invention, but be merely representative of selected embodiment of the invention.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without creative efforts belongs to the model that the present invention protects
It encloses.
Embodiment 1
The present embodiment discloses a kind of model building method, for establishing lane mould to three lanes to by high-precision map
Type, solution vehicle road in automatic Pilot should acquire element and be blocked, and in turn result in the problem that mistake occurs in Driving Decision-making.This
The specific implementation of embodiment method are as follows:
Step100, the basic geography information that road is loaded in GIS-Geographic Information System, establish the high-precision map of road, real
When acquisition vehicle location information and for matching vehicle in the real time position of high-precision map, real time position is mainly used for three
In lane, the current lane where vehicle and the location information in the other relatively current lane in two lanes are determined.
Step200, lane and other two lane configurations vehicles where vehicle in high-precision map are extracted according to real time position
The form point string of diatom;The earth coordinates such as Fig. 2 are specifically established, and under earth coordinates, form point string list is shown as
ShapePointWGS84 []={ pt1, pt2, pt3 ... }.
Step300, the coordinate set for being located at vehicle axis system according to form point information architecture lane.
Step310, referring to FIG. 3, establish vehicle axis system and under earth coordinates form point string convert: specific implementation
It is:
The x-axis of earth coordinates is rotated by 90 ° counterclockwise, y-axis rotates clockwise 90 degree;
Coordinate (x1, y1) under earth coordinates is extracted, vehicle body coordinate system (x2, y2) is transformed into;
Wherein, x2=y1*sin (angle), y2=x1*cos (angle), angle=atan (y1/x1);
Form point string under vehicle axis system is shapePoint []={ ptA, ptB, ptC ... }.
Step320, lane line equation is generated using curve fitting algorithm;
Step321, from the form point string of vehicle axis system, take a form point to be used at interval of 20cm in map with high precision
Curve matching.
Step322, the cubic polynomial that lane line equation is generated using the curve fitting algorithm of cubic Bezier principle;
The expression formula of cubic polynomial is y=C0+C1*X+C2*X*X+C3*X*X*X, and the value range of X arrives for MinX
MinX,
Wherein equation parameter includes that C0, C1, C3, C4 are coefficient, and X, Y are vehicle body coordinate system coordinate, and Minx is the minimum of X
Value, MaxX are the maximum value of X;
Step323, several form point strings substituted under vehicle axis system respectively calculate three for checking trinomial three times
The least mean-square error of order polynomial is equation parameter MSE.
Step400, conversion simultaneously communicate above-mentioned cubic polynomial and equation parameter to vehicle CAN bus, be vehicle from
Dynamic driving strategy provides strategic road information.
The conversion of parameter and equation parameter that the present embodiment is related to cubic polynomial is defined as following three CAN messages,
For communicating.
Through the above scheme, the method for the present embodiment is by the combination of accurately diagram data and vehicle location information
The automatic Pilot of vehicle provides the basic data model of more accurately environment sensing, behaviour decision making.
Embodiment two
The method of the present embodiment is further configured to be extracted according to real time position on the basis of the Step200 of embodiment one
Three lanes configure the attribute data in high-precision map, and attribute data includes at least actual situation, color and the lane change rule of lane line
It is one or more.
The present embodiment conversion and communication attribute data are to vehicle CAN bus;The conversion of attribute data can be defined as following
CAN message, for communicating.
Embodiment three
The present embodiment separately disclose a kind of computer can storage medium, it is for storing instruction, real when instruction is executed by processor
Now such as the step of two method of embodiment one or embodiment.
Example IV
A kind of lane model construction device, device include mapping module, load location data in high-precision map match vehicle
Real time position;Acquisition module extracts lane configurations in the form point information of high-precision map according to real time position;Model construction
Module is located at the coordinate set of vehicle axis system according to form point information architecture lane;Communication module is converted and communicates coordinate set to vehicle
CAN bus.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of lane model building method, for establishing the lane model of service automatic Pilot, which is characterized in that the side
Method:
Determine vehicle in the real time position of high-precision map;
Lane configurations are extracted in the form point information of the high-precision map according to the real time position;
It is located at the coordinate set of vehicle axis system according to form point information architecture lane;
It converts and communicates the coordinate set to vehicle CAN bus.
2. lane model building method as described in claim 1, which is characterized in that
Real time position of the determination vehicle in high-precision map, comprising:
Obtain the location data of vehicle;
Vehicle is matched in the real time position of the high-precision map according to the location data.
3. lane model building method as described in claim 1, which is characterized in that
Described extracts lane configurations in the form point information of the high-precision map according to the real time position, comprising:
The shape of current lane and the adjacent lane positioned at the current lane two sides where extracting vehicle according to the real time position
Point information.
4. lane model building method as described in claim 1, which is characterized in that
The coordinate set for being located at vehicle axis system according to form point information architecture lane, comprising:
The map coordinates system of the high-precision map is converted as vehicle body coordinate system,
Lane line equation is generated using curve fitting algorithm;
The conversion simultaneously communicates the coordinate set to vehicle CAN bus, comprising:
It converts and communicates the lane line equation to vehicle CAN bus.
5. lane model building method as claimed in claim 4, which is characterized in that
Described generates lane line equation using curve fitting algorithm, comprising:
The cubic polynomial of lane line equation is generated using the curve fitting algorithm of cubic Bezier principle,
The expression formula of the cubic polynomial is y=C0+C1*X+C2*X*X+C3*X*X*X, and the value range of X arrives for MinX
MinX,
Wherein equation parameter includes that C0, C1, C3, C4 are coefficient, and X, Y are vehicle body coordinate system coordinate, and Minx is the minimum value of X,
MaxX is the maximum value of X;
The conversion simultaneously communicates the coordinate set to vehicle CAN bus, comprising:
It converts and communicates the cubic polynomial and equation parameter to vehicle CAN bus.
6. lane model building method as claimed in claim 5, which is characterized in that
The curve fitting algorithm using cubic Bezier principle generates the cubic polynomial of lane line equation, in Hou Bao
It includes:
The form point information is substituted into the cubic polynomial, calculates the least mean-square error of the cubic polynomial as side
Journey parameter.
7. lane model building method as described in claim 1, which is characterized in that
Described extracts lane configurations in the form point information of the high-precision map according to the real time position, further includes:
Lane configurations are extracted in the attribute data of the high-precision map according to the real time position;
The conversion simultaneously communicates the coordinate set to vehicle CAN bus, further includes:
It converts and communicates the attribute data to vehicle CAN bus.
8. lane as claimed in claim 7 model building method, which is characterized in that
The attribute data includes at least the one or more of actual situation, color and the lane change rule of lane line.
9. a kind of computer can storage medium, for storing instruction, which is characterized in that realization when described instruction is executed by processor
Such as the step of claim 1-8 any one the method.
10. a kind of lane model construction device, which is characterized in that described device includes:
Mapping module, real time position of the load location data in high-precision map-matched automobile;
Acquisition module extracts lane configurations in the form point information of high-precision map according to real time position;
Model construction module is located at the coordinate set of vehicle axis system according to form point information architecture lane;
Communication module is converted and communicates coordinate set to vehicle CAN bus.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810950573.9A CN109297499A (en) | 2018-08-20 | 2018-08-20 | Lane model building method, device and computer can storage mediums |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810950573.9A CN109297499A (en) | 2018-08-20 | 2018-08-20 | Lane model building method, device and computer can storage mediums |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109297499A true CN109297499A (en) | 2019-02-01 |
Family
ID=65165268
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810950573.9A Pending CN109297499A (en) | 2018-08-20 | 2018-08-20 | Lane model building method, device and computer can storage mediums |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109297499A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109724615A (en) * | 2019-02-28 | 2019-05-07 | 北京经纬恒润科技有限公司 | A kind of method of calibration and system of Lane detection result |
CN110466516A (en) * | 2019-07-11 | 2019-11-19 | 北京交通大学 | A kind of curved road automatic vehicle lane-change method for planning track based on Non-Linear Programming |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8755967B1 (en) * | 2012-03-23 | 2014-06-17 | Google Inc. | Estimating road lane geometry using lane marker observations |
CN105270410A (en) * | 2014-07-16 | 2016-01-27 | 通用汽车环球科技运作有限责任公司 | Accurate curvature estimation algorithm for path planning of autonomous driving vehicle |
CN105774805A (en) * | 2014-09-12 | 2016-07-20 | 现代自动车株式会社 | System for estimating lane and method thereof |
CN107516078A (en) * | 2017-08-18 | 2017-12-26 | 电子科技大学 | A kind of lane detection fixing method |
CN107914600A (en) * | 2016-10-11 | 2018-04-17 | 上海汽车集团股份有限公司 | Roadmarking coordinate automatic acquisition equipment, collection control method and control device |
CN108297866A (en) * | 2018-01-03 | 2018-07-20 | 西安交通大学 | A kind of track holding control method of vehicle |
CN108387242A (en) * | 2018-02-07 | 2018-08-10 | 西南交通大学 | Automatic Pilot lane-change prepares and executes integrated method for planning track |
-
2018
- 2018-08-20 CN CN201810950573.9A patent/CN109297499A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8755967B1 (en) * | 2012-03-23 | 2014-06-17 | Google Inc. | Estimating road lane geometry using lane marker observations |
CN105270410A (en) * | 2014-07-16 | 2016-01-27 | 通用汽车环球科技运作有限责任公司 | Accurate curvature estimation algorithm for path planning of autonomous driving vehicle |
CN105774805A (en) * | 2014-09-12 | 2016-07-20 | 现代自动车株式会社 | System for estimating lane and method thereof |
CN107914600A (en) * | 2016-10-11 | 2018-04-17 | 上海汽车集团股份有限公司 | Roadmarking coordinate automatic acquisition equipment, collection control method and control device |
CN107516078A (en) * | 2017-08-18 | 2017-12-26 | 电子科技大学 | A kind of lane detection fixing method |
CN108297866A (en) * | 2018-01-03 | 2018-07-20 | 西安交通大学 | A kind of track holding control method of vehicle |
CN108387242A (en) * | 2018-02-07 | 2018-08-10 | 西南交通大学 | Automatic Pilot lane-change prepares and executes integrated method for planning track |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109724615A (en) * | 2019-02-28 | 2019-05-07 | 北京经纬恒润科技有限公司 | A kind of method of calibration and system of Lane detection result |
CN109724615B (en) * | 2019-02-28 | 2021-06-29 | 北京经纬恒润科技股份有限公司 | Method and system for verifying lane line identification result |
CN110466516A (en) * | 2019-07-11 | 2019-11-19 | 北京交通大学 | A kind of curved road automatic vehicle lane-change method for planning track based on Non-Linear Programming |
CN110466516B (en) * | 2019-07-11 | 2020-08-28 | 北京交通大学 | Curve road automatic vehicle lane change track planning method based on nonlinear programming |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106767853B (en) | Unmanned vehicle high-precision positioning method based on multi-information fusion | |
CN105206108B (en) | A kind of vehicle collision prewarning method based on electronic map | |
US9423260B2 (en) | Rating of map information | |
CN106352867B (en) | Method and device for determining the position of a vehicle | |
CN104819724B (en) | A kind of autonomous travel assist system of Unmanned Ground Vehicle based on GIS | |
US11808581B2 (en) | Lane-level map matching | |
CN104392625B (en) | A kind of Vehicular automatic driving system based on multiple sensors and method | |
CN108445503A (en) | The unmanned path planning algorithm merged with high-precision map based on laser radar | |
US7483790B2 (en) | Systems and methods for constructing variable offset paths | |
US11847838B2 (en) | Recognition device | |
US20120245756A1 (en) | Driver assistance system | |
CN109031304A (en) | Vehicle positioning method in view-based access control model and the tunnel of millimetre-wave radar map feature | |
CN105157709A (en) | ADASIS (advanced driver assistance systems interface specifications) extended information output device and method based on safe driving map | |
CN103940434A (en) | Real-time lane line detecting system based on monocular vision and inertial navigation unit | |
US11747166B2 (en) | Driving environment information generation method, driving control method, driving environment information generation device | |
CN109297499A (en) | Lane model building method, device and computer can storage mediums | |
CN104464375B (en) | It is a kind of to recognize the method that vehicle high-speed is turned | |
US20220057230A1 (en) | Method For Checking Detected Changes To An Environmental Model Of A Digital Area Map | |
CN110243380A (en) | A kind of map-matching method based on multi-sensor data and angle character identification | |
CN110415541A (en) | A kind of crossing prevailing state reminding method and system | |
JP7462396B2 (en) | Method and apparatus for operating a vehicle | |
CN111717244A (en) | Train automatic driving sensing method and system | |
JP7260064B2 (en) | Own vehicle position estimation device, running position estimation method | |
Bresson et al. | A cooperative fusion architecture for robust localization: Application to autonomous driving | |
TW202014676A (en) | Ship navigation system and method thereof |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190201 |